Merge branch 'HEAD' into archived_gym_leaderboard

StepNeverStop · Aug 27, 2021 · 7055ae4 · 7055ae4
2 parents 4db1c45 + a1e8c1e
commit 7055ae4
Show file tree

Hide file tree

Showing 5 changed files with 5 additions and 5 deletions.
diff --git a/gym_Leaderboard/CartPole-v0/README.md b/gym_Leaderboard/CartPole-v0/README.md
@@ -2,7 +2,7 @@
 
 - Convergence episode: 0
 - max step per episode: 200
-- algorithm: td3+gumbel[[code]( https://github.com/StepNeverStop/RLs/blob/master/Algorithms/tf2algos/td3.py )]
+- algorithm: td3+gumbel[[code]( https://github.com/StepNeverStop/RLs/tree/archived_gym_leaderboard/Algorithms/tf2algos/td3.py )]
 - Actor
 - - 64 -> 32 -> logits
 - Critic

diff --git a/gym_Leaderboard/LunarLander-v2/README.md b/gym_Leaderboard/LunarLander-v2/README.md
@@ -2,7 +2,7 @@
 
 - Convergence episode: 16
 - max step per episode: 1000
-- algorithm: sac+gumbel[[code]( https://github.com/StepNeverStop/RLs/blob/master/Algorithms/tf2algos/sac.py )]
+- algorithm: sac+gumbel[[code]( https://github.com/StepNeverStop/RLs/tree/archived_gym_leaderboard/Algorithms/tf2algos/sac.py )]
 - Actor
 - - 64 -> 32 -> logits
 - Critic_Q

diff --git a/gym_Leaderboard/LunarLanderContinuous-v2/README.md b/gym_Leaderboard/LunarLanderContinuous-v2/README.md
@@ -2,7 +2,7 @@
 
 - Convergence episode: 30
 - max step per episode: 1000
-- algorithm: sac[[code]( https://github.com/StepNeverStop/RLs/blob/master/Algorithms/tf2algos/sac.py )]
+- algorithm: sac[[code]( https://github.com/StepNeverStop/RLs/tree/archived_gym_leaderboard/Algorithms/tf2algos/sac.py )]
 - Actor
 - - 64(share) -> 64(share) -> 32 -> 32 -> mu(tanh)
 - - 64(share) -> 64(share) -> 32 -> 32 -> sigma(sigmoid)

diff --git a/gym_Leaderboard/MountainCar-v0/README.md b/gym_Leaderboard/MountainCar-v0/README.md
@@ -2,7 +2,7 @@
 
 - Convergence episode: 47
 - max step per episode: 200
-- algorithm: maxsqn[[code]( https://github.com/StepNeverStop/RLs/blob/master/Algorithms/tf2algos/maxsqn.py )], reimplementation from [createamind]( https://github.com/createamind/DRL/blob/master/spinup/algos/maxsqn/maxsqn.py )
+- algorithm: maxsqn[[code]( https://github.com/StepNeverStop/RLs/tree/archived_gym_leaderboard/Algorithms/tf2algos/maxsqn.py )], reimplementation from [createamind]( https://github.com/createamind/DRL/blob/master/spinup/algos/maxsqn/maxsqn.py )
 - Q:
 - - 32 -> 32 -> logits
 - n_step: 4

diff --git a/gym_Leaderboard/MountainCarContinuous-v0/README.md b/gym_Leaderboard/MountainCarContinuous-v0/README.md
@@ -2,7 +2,7 @@
 
 - Convergence episode: 11
 - max step per episode: 999
-- algorithm: sac[[code]( https://github.com/StepNeverStop/RLs/blob/master/Algorithms/tf2algos/sac.py )]
+- algorithm: sac[[code]( https://github.com/StepNeverStop/RLs/tree/archived_gym_leaderboard/Algorithms/tf2algos/sac.py )]
 - Actor
 - - 64(share) -> 64(share) -> 32 -> 32 -> mu(tanh)
 - - 64(share) -> 64(share) -> 32 -> 32 -> sigma(sigmoid)